def test_process_pedline_relationship(self):
"""Test a pedline with father or mother ids"""
father, mother, child = self.get_relationships()
# process data and insert records
for i, item in enumerate([father, mother, child]):
test = self.plinkio._process_pedline(item, self.dataset, 'top')
# define smarter_id
smarter_id = f"ITOA-TEX-00000000{i+1}"
# test ped line items
self.assertEqual(test[0], "TEX")
self.assertEqual(test[1], smarter_id)
self.assertEqual(test[4], item[4])
# assert database objects
sample = SampleSheep.objects(smarter_id=smarter_id).get()
# special child case
if item == child:
sample_father = SampleSheep.objects(
original_id=item[2], dataset=self.dataset).get()
sample_mother = SampleSheep.objects(
original_id=item[3], dataset=self.dataset).get()
self.assertIsNone(sample.sex)
self.assertEqual(sample.father_id, sample_father)
self.assertEqual(sample.mother_id, sample_mother)
self.assertEqual(test[2], sample_father.smarter_id)
self.assertEqual(test[3], sample_mother.smarter_id)
else:
self.assertEqual(sample.sex, SEX(int(item[4])))
def setUp(self):
self.runner = CliRunner()
# add a sample in database
self.sample = SampleSheep(
original_id="test-1",
country="Italy",
species="Sheep",
breed="Texel",
breed_code="TEX",
dataset=self.dst_dataset,
chip_name=self.chip_name,
)
self.sample.save()
def setUp(self):
self.runner = CliRunner()
# need also a sample
self.sample = SampleSheep(
original_id="test-1",
smarter_id="ITOA-TEX-000000001",
country="Italy",
species="Sheep",
breed="Texel",
breed_code="TEX",
dataset=self.dst_dataset,
chip_name=self.chip_name,
)
self.sample.save()
def test_update_relationship(self):
"""Test the possibility to update a sample relationship"""
# ped lines could be in the wrong order. In such way, a child sample
# could be written before its parents, and so ped lines can't be
# written correctly
# define fake relationships
father, mother, child = self.get_relationships()
# process data and insert records
for i, item in enumerate([child, father, mother]):
self.plinkio._process_pedline(item, self.dataset, 'top')
# special child case
if item == child:
# define smarter_id
smarter_id = f"ITOA-TEX-00000000{i+1}"
# assert database objects
sample_child = SampleSheep.objects(smarter_id=smarter_id).get()
# assert child has no relationship
self.assertIsNone(sample_child.father_id)
self.assertIsNone(sample_child.mother_id)
self.assertIsNone(sample_child.sex)
# ok now try to process child again
test = self.plinkio._process_pedline(child, self.dataset, 'top')
# refresh database object
sample_child.reload()
sample_father = sample_child.father_id.fetch()
sample_mother = sample_child.mother_id.fetch()
self.assertEqual(sample_child.smarter_id, test[1])
self.assertEqual(sample_father.smarter_id, test[2])
self.assertEqual(sample_mother.smarter_id, test[3])
class TestImportSamples(
SmarterIDMixin, IlluminaChipMixin, MongoMockMixin, unittest.TestCase):
@classmethod
def setUpClass(cls):
super().setUpClass()
# getting destination dataset
cls.dst_dataset = Dataset.objects.get(file="test.zip")
# create a src dataset
cls.src_dataset = Dataset(
file="test2.zip",
country="Italy",
species="Sheep",
contents=[
"metadata.xlsx"
]
)
cls.src_dataset.save()
# create a workbook
cls.workbook = Workbook()
cls.sheet = cls.workbook.active
# adding header
cls.sheet.cell(row=1, column=1, value="Code")
cls.sheet.cell(row=1, column=2, value="Id")
cls.sheet.cell(row=1, column=3, value="Country")
cls.sheet.cell(row=1, column=4, value="Sex")
# adding values
cls.sheet.cell(row=2, column=1, value="TEX_IT")
cls.sheet.cell(row=2, column=2, value="test-1")
cls.sheet.cell(row=2, column=3, value="Italy")
cls.sheet.cell(row=2, column=4, value="BHO")
# adding values
cls.sheet.cell(row=3, column=1, value="TEX_IT")
cls.sheet.cell(row=3, column=2, value="test-2")
cls.sheet.cell(row=3, column=3, value="SPAIN")
cls.sheet.cell(row=3, column=4, value="F")
def setUp(self):
self.runner = CliRunner()
# add a sample in database
self.sample = SampleSheep(
original_id="test-1",
country="Italy",
species="Sheep",
breed="Texel",
breed_code="TEX",
dataset=self.dst_dataset,
chip_name=self.chip_name,
)
self.sample.save()
def tearDown(self):
SampleSheep.objects.delete()
super().tearDown()
def test_help(self):
result = self.runner.invoke(import_samples, ["--help"])
self.assertEqual(0, result.exit_code)
self.assertIn('Usage: main', result.output)
@patch('src.features.smarterdb.Dataset.working_dir',
new_callable=PropertyMock)
def test_import_mandatory(self, my_working_dir):
# create a temporary directory using the context manager
with tempfile.TemporaryDirectory() as tmpdirname:
working_dir = pathlib.Path(tmpdirname)
my_working_dir.return_value = working_dir
# save worksheet in temporary folder
self.workbook.save(f"{working_dir}/metadata.xlsx")
# got first sample from database
self.assertEqual(SampleSheep.objects.count(), 1)
result = self.runner.invoke(
import_samples,
[
"--src_dataset",
"test2.zip",
"--dst_dataset",
"test.zip",
"--datafile",
"metadata.xlsx",
"--code_column",
"Code",
"--country_column",
"Country",
"--id_column",
"Id",
"--chip_name",
self.chip_name
]
)
self.assertEqual(0, result.exit_code, msg=result.exception)
# I should have two record for samples, One already present one new
self.assertEqual(SampleSheep.objects.count(), 2)
# get the new sample
sample = SampleSheep.objects.get(original_id="test-2")
self.assertEqual(sample.smarter_id, "ESOA-TEX-000000002")
@patch('src.features.smarterdb.Dataset.working_dir',
new_callable=PropertyMock)
def test_import_with_sex(self, my_working_dir):
# create a temporary directory using the context manager
with tempfile.TemporaryDirectory() as tmpdirname:
working_dir = pathlib.Path(tmpdirname)
my_working_dir.return_value = working_dir
# save worksheet in temporary folder
self.workbook.save(f"{working_dir}/metadata.xlsx")
# got first sample from database
self.assertEqual(SampleSheep.objects.count(), 1)
result = self.runner.invoke(
import_samples,
[
"--src_dataset",
"test2.zip",
"--dst_dataset",
"test.zip",
"--datafile",
"metadata.xlsx",
"--code_column",
"Code",
"--country_column",
"Country",
"--id_column",
"Id",
"--sex_column",
"Sex",
"--chip_name",
self.chip_name
]
)
self.assertEqual(0, result.exit_code, msg=result.exception)
# I should have two record for samples, One already present one new
self.assertEqual(SampleSheep.objects.count(), 2)
# first sampla wasn't been updated. Unknown sex
self.sample.reload()
self.assertIsNone(self.sample.sex)
# get the new sample
sample = SampleSheep.objects.get(original_id="test-2")
self.assertEqual(sample.smarter_id, "ESOA-TEX-000000002")
self.assertEqual(sample.sex, SEX.FEMALE)
class PhenotypeMixin(SmarterIDMixin, IlluminaChipMixin, MongoMockMixin):
@classmethod
def setUpClass(cls):
super().setUpClass()
# getting destination dataset
cls.dst_dataset = Dataset.objects.get(file="test.zip")
# create a src dataset
cls.src_dataset = Dataset(file="test2.zip",
country="Italy",
species="Sheep",
contents=["phenotypes.xlsx"])
cls.src_dataset.save()
# create a workbook
cls.workbook = Workbook()
cls.sheet = cls.workbook.active
# adding header
cls.sheet.cell(row=1, column=1, value="Code")
cls.sheet.cell(row=1, column=2, value="Name")
cls.sheet.cell(row=1, column=3, value="Country")
cls.sheet.cell(row=1, column=4, value="Id")
cls.sheet.cell(row=1, column=5, value="ChestGirth")
cls.sheet.cell(row=1, column=6, value="Height")
cls.sheet.cell(row=1, column=7, value="Length")
cls.sheet.cell(row=1, column=8, value="WidthOfPinBones")
cls.sheet.cell(row=1, column=9, value="FAMACHA")
cls.sheet.cell(row=1, column=10, value="Purpose")
# adding values
cls.sheet.cell(row=2, column=1, value="TEX")
cls.sheet.cell(row=2, column=2, value="Texel")
cls.sheet.cell(row=2, column=3, value="Italy")
cls.sheet.cell(row=2, column=4, value="test-1")
cls.sheet.cell(row=2, column=5, value=77.5)
cls.sheet.cell(row=2, column=6, value=60.5)
cls.sheet.cell(row=2, column=7, value=69.5)
cls.sheet.cell(row=2, column=8, value=16)
cls.sheet.cell(row=2, column=9, value="D")
cls.sheet.cell(row=2, column=10, value="Milk")
@classmethod
def tearDownClass(cls):
Dataset.objects.delete()
SampleSheep.objects.delete()
super().tearDownClass()
def setUp(self):
self.runner = CliRunner()
# need also a sample
self.sample = SampleSheep(
original_id="test-1",
smarter_id="ITOA-TEX-000000001",
country="Italy",
species="Sheep",
breed="Texel",
breed_code="TEX",
dataset=self.dst_dataset,
chip_name=self.chip_name,
)
self.sample.save()
def tearDown(self):
SampleSheep.objects.delete()
super().tearDown()
class MetaDataMixin(SmarterIDMixin, IlluminaChipMixin, MongoMockMixin):
@classmethod
def setUpClass(cls):
super().setUpClass()
# getting destination dataset
cls.dst_dataset = Dataset.objects.get(file="test.zip")
# create a src dataset
cls.src_dataset = Dataset(file="test2.zip",
country="Italy",
species="Sheep",
contents=["metadata.xlsx"])
cls.src_dataset.save()
# create a workbook
cls.workbook = Workbook()
cls.sheet = cls.workbook.active
# adding header
cls.sheet.cell(row=1, column=1, value="Code")
cls.sheet.cell(row=1, column=2, value="Name")
cls.sheet.cell(row=1, column=3, value="Country")
cls.sheet.cell(row=1, column=4, value="Lat")
cls.sheet.cell(row=1, column=5, value="Lon")
cls.sheet.cell(row=1, column=6, value="Col1")
cls.sheet.cell(row=1, column=7, value="Col 2")
cls.sheet.cell(row=1, column=8, value="Id")
# adding values
cls.sheet.cell(row=2, column=1, value="TEX")
cls.sheet.cell(row=2, column=2, value="Texel")
cls.sheet.cell(row=2, column=3, value="Italy")
cls.sheet.cell(row=2, column=4, value=45.46427)
cls.sheet.cell(row=2, column=5, value=9.18951)
cls.sheet.cell(row=2, column=6, value="Val1")
cls.sheet.cell(row=2, column=7, value="Val2")
cls.sheet.cell(row=2, column=8, value="test-1")
@classmethod
def tearDownClass(cls):
Dataset.objects.delete()
SampleSheep.objects.delete()
super().tearDownClass()
def setUp(self):
self.runner = CliRunner()
# need also a sample
self.sample = SampleSheep(
original_id="test-1",
smarter_id="ITOA-TEX-000000001",
country="Italy",
species="Sheep",
breed="Texel",
breed_code="TEX",
dataset=self.dst_dataset,
chip_name=self.chip_name,
)
self.sample.save()
def tearDown(self):
SampleSheep.objects.delete()
super().tearDown()